[CLI] simplify docker run (#159)

* bake run.yaml inside docker, simplify run

* add docker template examples

* delete generated Dockerfile

* unique deps

* clean up debug

* default entrypoint

* address comments, update output msg

* update msg

* build output msg

* configure msg

* unique special_deps

* remove quotes in configure

llama_stack/distribution/templates/docker/llamastack-local-cpu/build.yaml

@@ -0,0 +1,15 @@
+name: local-cpu
+distribution_spec:
+  description: remote inference + local safety/agents/memory
+  docker_image: null
+  providers:
+    inference:
+    - remote::ollama
+    - remote::tgi
+    - remote::together
+    - remote::fireworks
+    safety: meta-reference
+    agents: meta-reference
+    memory: meta-reference
+    telemetry: meta-reference
+image_type: docker

llama_stack/distribution/templates/docker/llamastack-local-cpu/run.yaml

@@ -0,0 +1,64 @@
+built_at: '2024-09-30T09:04:30.533391'
+image_name: local-cpu
+docker_image: local-cpu
+conda_env: null
+apis_to_serve:
+- agents
+- inference
+- models
+- memory
+- safety
+- shields
+- memory_banks
+api_providers:
+  inference:
+    providers:
+    - remote::ollama
+  safety:
+    providers:
+    - meta-reference
+  agents:
+    provider_id: meta-reference
+    config:
+      persistence_store:
+        namespace: null
+        type: sqlite
+        db_path: /home/xiyan/.llama/runtime/kvstore.db
+  memory:
+    providers:
+    - meta-reference
+  telemetry:
+    provider_id: meta-reference
+    config: {}
+routing_table:
+  inference:
+  - provider_id: remote::ollama
+    config:
+      host: localhost
+      port: 6000
+    routing_key: Meta-Llama3.1-8B-Instruct
+  safety:
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: llama_guard
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: code_scanner_guard
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: injection_shield
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: jailbreak_shield
+  memory:
+  - provider_id: meta-reference
+    config: {}
+    routing_key: vector

llama_stack/distribution/templates/docker/llamastack-local-gpu/build.yaml

@@ -0,0 +1,11 @@
+name: local-gpu
+distribution_spec:
+  description: local meta reference
+  docker_image: null
+  providers:
+    inference: meta-reference
+    safety: meta-reference
+    agents: meta-reference
+    memory: meta-reference
+    telemetry: meta-reference
+image_type: docker

llama_stack/distribution/templates/docker/llamastack-local-gpu/run.yaml

@@ -0,0 +1,67 @@
+built_at: '2024-09-30T09:00:56.693751'
+image_name: local-gpu
+docker_image: local-gpu
+conda_env: null
+apis_to_serve:
+- memory
+- inference
+- agents
+- shields
+- safety
+- models
+- memory_banks
+api_providers:
+  inference:
+    providers:
+    - meta-reference
+  safety:
+    providers:
+    - meta-reference
+  agents:
+    provider_id: meta-reference
+    config:
+      persistence_store:
+        namespace: null
+        type: sqlite
+        db_path: /home/xiyan/.llama/runtime/kvstore.db
+  memory:
+    providers:
+    - meta-reference
+  telemetry:
+    provider_id: meta-reference
+    config: {}
+routing_table:
+  inference:
+  - provider_id: meta-reference
+    config:
+      model: Llama3.1-8B-Instruct
+      quantization: null
+      torch_seed: null
+      max_seq_len: 4096
+      max_batch_size: 1
+    routing_key: Llama3.1-8B-Instruct
+  safety:
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: llama_guard
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: code_scanner_guard
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: injection_shield
+  - provider_id: meta-reference
+    config:
+      llama_guard_shield: null
+      prompt_guard_shield: null
+    routing_key: jailbreak_shield
+  memory:
+  - provider_id: meta-reference
+    config: {}
+    routing_key: vector